The test video of 22 seconds took 9 minutes. The lip-syncing actions turned out well. You only need to upload images and audio. Everything else is set up and doesn't need modification. Everyone can use a few seconds of audio for each segment to make the images move. 5 to 6 seconds per scene is suitable for novel promotion voiceovers and works quite well.

If you don't have high-quality voiceovers, come here to clone: https://www.runninghub.cn/ai detail/1912339233200373762